CN212379309U - Boiler heating surface appearance defect on-line measuring and recognition device - Google Patents
Boiler heating surface appearance defect on-line measuring and recognition device Download PDFInfo
- Publication number
- CN212379309U CN212379309U CN202020598939.3U CN202020598939U CN212379309U CN 212379309 U CN212379309 U CN 212379309U CN 202020598939 U CN202020598939 U CN 202020598939U CN 212379309 U CN212379309 U CN 212379309U
- Authority
- CN
- China
- Prior art keywords
- boiler
- heating surface
- defect
- appearance
- camera
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Landscapes
- Investigating Or Analyzing Materials Using Thermal Means (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The utility model discloses a boiler receives hot side appearance defect on-line measuring and recognition device carries on high definition camera and light filling device through receiving hot side detection robot at the boiler, can carry out data acquisition to the boiler receives hot side outward appearance automatically to utilize degree of depth learning algorithm to establish defect identification model, realize appearance defect's on-line identification. The device comprises a high-definition camera, a light supplementing device, an ultra-computation chip, a device shell and an external connecting plate. Under the influence of the environment, a high-definition explosion-proof camera with an automatic zooming function is selected as a camera, and appearance information of the heating surface of the boiler is acquired by matching with a light supplementing device; and a deep learning algorithm based on image recognition and analysis is integrated in the super-computation chip and used for recognizing defect information. High definition camera, light filling device and super calculation chip are all integrated to the device shell in the middle of, this device of outer connecting plate and removal body fixed connection. Because the operational environment is the dangerous environment of high dustiness, this device all adopts explosion-proof design.
Description
Technical Field
The utility model relates to a boiler heating surface appearance imperfections on-line measuring and recognition device belongs to boiler technical field.
Background
At present, the installed capacity of the domestic thermal power machine accounts for 58% of the total installed capacity of electric power, and the thermal power machine is a support for electric power supply in China and has important significance for guaranteeing safe electric energy supply. The failure of the heating surface of the boiler is the main cause of the unplanned shutdown of the unit.
The traditional detection work of the heating surface of the boiler is observed by the naked eyes of operators, and mainly faces the following problems:
(1) before detection, a large amount of time is needed for building and dismantling the operation platform, and the workload is large;
(2) the area of the heating surface of the boiler is large, the time for complete inspection is long, and the detection efficiency is low;
(3) the environment inside the boiler is severe, the dust is serious, and the operation safety risk exists for detection personnel;
(4) the interior of the boiler is sealed and lightless, so that the sight line of human eyes and an observation result are seriously influenced;
(5) the manual inspection is difficult to form perfect digital record, which is not beneficial to tracking the state of the furnace tube for a long time.
In view of this, the device for online detection and identification of the appearance defects of the heating surface of the boiler is designed, so that the automatic identification of the appearance defects of the heating surface of the boiler can be completed online, and a maintainer is guided to accurately perform fault treatment.
SUMMERY OF THE UTILITY MODEL
The to-be-solved technical problem of the utility model is how to realize the data acquisition of boiler heating surface appearance information, establish the appearance defect knowledge base, discern the screening through the degree of depth learning algorithm, realize boiler appearance defect on-line identification.
In order to solve the technical problem, the technical scheme of the utility model provide a boiler receives hot side appearance defect on-line measuring and recognition device is provided, through carrying on high definition camera and light filling device at boiler receiving hot side detection robot, can carry out data acquisition to boiler receiving hot side outward appearance automatically to utilize the degree of depth learning algorithm to establish defect recognition model, realize appearance defect's on-line identification.
The device of the utility model includes: high definition camera, light filling device, super calculation chip, device shell and outer connecting plate. Under the influence of the environment, a high-definition explosion-proof camera with an automatic zooming function is selected as a camera, and appearance information of the heating surface of the boiler is acquired by matching with a light supplementing device; and a deep learning algorithm based on image recognition and analysis is integrated in the super-computation chip and used for recognizing defect information. High definition camera, light filling device and super calculation chip are all integrated to the device shell in the middle of, this device of outer connecting plate and removal body fixed connection. Because the operational environment is the dangerous environment of high dustiness, this device all adopts explosion-proof design.
And the image information acquired by the device is subjected to simple image processing, and compared with a defect library model by using a deep learning algorithm in an overcomputing chip, so that online identification is finally realized.
Compared with the prior art, the utility model has the advantages that:
(1) calculating the characteristics of the defects from the appearance of the heating surface of the boiler by adopting a deep learning technology, and coding the characteristics to realize high-precision on-line calculation of the appearance defect codes of the heating surface of the boiler;
(2) and (3) performing a deep learning algorithm to realize intelligent recognition of the appearance defects of the furnace tube. The false detection rate is low, the target detection rate is more than 90%, and the recognition speed is far higher than that of manual detection. The method is initiated in China, and is used for training a heating surface sample by using a machine learning algorithm, extracting state characteristics and developing an automatic recognition algorithm of the heating surface state characteristics.
(3) Producing a great deal of economic benefit. The time required by the overall appearance inspection of the whole boiler is greatly shortened, the downtime is reduced, and the furnace shutdown loss is reduced. The inspection operation is carried out by using short unit shutdown time: adopt unmanned aerial vehicle to replace people to detect, reduced the furnace lift and overhauld the setting up of platform, demolish and relevant preparation work.
(4) The man-machine safety is greatly improved. Patrol and examine unmanned aerial vehicle and gather a large amount of boiler tube health data, including measurement data and image data such as appearance imperfections, support power plant boiler state and overhaul, improve equipment security reduces the non-risk of stopping of boiler. Reduce the testing personnel safety risk, ensure personnel are healthy: the intelligent unmanned detection is adopted, so that the region which can not be reached manually can be reached, and the detection range is expanded, thereby reducing the unplanned shutdown of the boiler and improving the safety of equipment; the workload of the workers is reduced, and the safety of the workers is improved.
Drawings
FIG. 1 is a schematic structural view of an on-line detecting and identifying device for appearance defects of a heating surface of a boiler according to the present invention;
reference numerals: the device comprises a device shell 1, an explosion-proof Glan head 2, a 3-definition camera, an external connecting plate 4, a 5-degree super computing chip and a 6-degree light supplementing device;
fig. 2 is a flow chart of the utility model of a boiler heating surface appearance defect on-line detection and identification device.
Detailed Description
In order to make the present invention more comprehensible, preferred embodiments are described in detail below with reference to the accompanying drawings.
Examples
Fig. 1 is a schematic structural view of the online detection and identification device for the appearance defect of the heating surface of the boiler of the present invention, wherein the camera 3 selects a high-definition explosion-proof camera 3 with an automatic zooming function, and is matched with a light supplement device 6 to realize the acquisition of the appearance information of the heating surface of the boiler; the super-computation chip 5 is internally integrated with a deep learning algorithm based on image recognition and analysis and used for recognizing defect information. High definition camera 3, light filling device 6 and super chip 5 are all integrated to in the middle of device shell 1, outer connecting plate 4 and removal body fixed connection. Because the working environment is a high-dust dangerous environment, the device is designed to be explosion-proof, and the shell 1 of the device is provided with an explosion-proof gland head 2 for information transmission.
FIG. 2 is a flow chart of the operation of the apparatus for online detection and identification of appearance defects of a heating surface of a boiler in accordance with the present invention; firstly, the utility model discloses the device is installed on the mobile device (can be dolly/unmanned aerial vehicle/manual work). When the work starts, mainly utilize high definition camera to carry out image extraction to the environment that is located, the image of extracting mainly has 2 parts effects: 1. calibrating and identifying the defects of the obtained picture and the prior picture, and establishing and perfecting a knowledge base of appearance defects of the heating surface of the boiler; 2. and the image is enhanced and balanced by using an algorithm to obtain a clearer image, and then the clearer image is compared with a defect model in a defect library for identification, so that the purposes of online detection and identification are achieved.
The utility model discloses the key improvement point of creation lies in designing a boiler heating surface appearance defect on-line measuring and recognition device, can detect and discern boiler heating surface appearance defect on line in real time.
Key improvements are as follows:
(1) performing image processing and defect identification and calibration through a large number of existing defect pictures to obtain an appearance defect characteristic model of the heating surface of the boiler, establishing an appearance defect model of the heating surface of the boiler, and automatically identifying the appearance of the heating surface;
(2) with the proceeding of the detection operation of the heating surface of the boiler, a large number of defect information samples are obtained, namely appearance defect data information is increased, and the accuracy of identification can be continuously updated through continuous learning of a deep learning algorithm;
(3) from the whole system, an appearance database of the heating surface of the boiler is established, and the boiler maintenance management level is improved.
Claims (2)
1. The on-line detection and identification device for the appearance defects of the heating surface of the boiler is characterized by comprising a high-definition camera (3), a light supplementing device (6), an ultra-computation chip (5), a device shell (1) and an external connecting plate (4), wherein the high-definition camera (3), the light supplementing device (6) and the ultra-computation chip (5) are all arranged on the device shell (1), and the external connecting plate (4) connected with a moving device is arranged on one side of the device shell (1); the device shell (1) is also provided with an explosion-proof Glan head (2) for information transmission.
2. The on-line detection and identification device for the appearance defects of the heating surface of the boiler as claimed in claim 1, wherein the high-definition camera (3) is a high-definition explosion-proof camera with an automatic zooming function.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202020598939.3U CN212379309U (en) | 2020-04-20 | 2020-04-20 | Boiler heating surface appearance defect on-line measuring and recognition device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202020598939.3U CN212379309U (en) | 2020-04-20 | 2020-04-20 | Boiler heating surface appearance defect on-line measuring and recognition device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN212379309U true CN212379309U (en) | 2021-01-19 |
Family
ID=74160562
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202020598939.3U Active CN212379309U (en) | 2020-04-20 | 2020-04-20 | Boiler heating surface appearance defect on-line measuring and recognition device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN212379309U (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112884036A (en) * | 2021-02-09 | 2021-06-01 | 北京京能能源技术研究有限责任公司 | Boiler heating surface abnormal image identification method, marking method and system |
| CN113658094A (en) * | 2021-07-06 | 2021-11-16 | 大唐东北电力试验研究院有限公司 | Thermal power plant boiler four-pipe intelligent detection method based on vision |
-
2020
- 2020-04-20 CN CN202020598939.3U patent/CN212379309U/en active Active
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112884036A (en) * | 2021-02-09 | 2021-06-01 | 北京京能能源技术研究有限责任公司 | Boiler heating surface abnormal image identification method, marking method and system |
| CN113658094A (en) * | 2021-07-06 | 2021-11-16 | 大唐东北电力试验研究院有限公司 | Thermal power plant boiler four-pipe intelligent detection method based on vision |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN212379309U (en) | Boiler heating surface appearance defect on-line measuring and recognition device | |
| CN104390657B (en) | A kind of Generator Unit Operating Parameters measurement sensor fault diagnosis method and system | |
| CN107782733A (en) | Image recognition the cannot-harm-detection device and method of cracks of metal surface | |
| CN105463514B (en) | A kind of aluminium electrolysis cell condition automatic detecting method and its device | |
| CN111426699A (en) | Boiler heating surface appearance defect online detection and identification device and method | |
| CN106371013A (en) | Picture identification-based GIS switch fault automatic identification system | |
| CN104535589A (en) | Online detection method and device for low-voltage current mutual inductor | |
| CN113688817A (en) | Instrument identification method and system for automatic inspection | |
| CN111127445A (en) | Distribution network line high-temperature area detection method and system based on deep learning | |
| CN205175925U (en) | Fabric defects real -time detection device | |
| CN111124015A (en) | Intelligent wind power inspection video monitoring method | |
| CN111754737A (en) | Online identification and evaluation device and method for installation acceptance of metering device | |
| CN104897463A (en) | Real-time detection apparatus and real-time detection method of steel-concrete combination member deformation due to force applying | |
| CN116152202A (en) | Equipment appearance detection system based on image recognition technology and infrared thermal imaging technology | |
| CN205909857U (en) | Intelligent all -round real -time monitoring system of power plant | |
| CN113469938A (en) | Pipe gallery video analysis method and system based on embedded front-end processing server | |
| CN116641855B (en) | Wind generating set operation monitoring method, system, equipment and storage medium | |
| CN108507725A (en) | A kind of sulfur hexafluoride gas Leakage Detection device | |
| CN106774190A (en) | Wet cooling gas turbine group condenser vacuum exception auto-check system and method | |
| CN206224226U (en) | Wet cooling gas turbine group condenser vacuum exception auto-check system | |
| CN111028289B (en) | Method for positioning foreign matters in equipment in transformer substation based on template matching | |
| Liang et al. | Research on Surface Defect Detection Algorithm of Tube-Type Bottle Based on Machine Vision | |
| CN206546417U (en) | A kind of GIS switch fault automatic recognition systems based on picture recognition | |
| CN208314857U (en) | Artificial intelligence pattern recognition device towards the online position detection of photovoltaic cell | |
| CN201060089Y (en) | Laser image-forming SF6 leakage positioning apparatus |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| GR01 | Patent grant | ||
| GR01 | Patent grant |